agentleFS
seancabalseseancabalse/agentic-playbook/skills/log-decision/SKILL.md

log-decision

Skill0 starsChanged 15 days agoMITView on GitHub

Record a decision or an accepted risk in the decision log. Use when the owner or the team makes a decision.

8 other projects use a version of this.

Adopted by

Most recently taken up by

The file

Files
SKILL.md

Log a decision

Playbook files named here: when the project has its own copy at .playbook/local/<same path>, use that copy instead.

Decision: $ARGUMENTS

  1. Classify it:
    • Product: what customers get; the owner decided.
    • Technical: how it's built.
    • Process: how we work.
    • Accepted risk: a known issue we're living with.
    • Hard to reverse? Use write-adr instead and log a pointer.
  2. Write the row at the top of the right section (${CLAUDE_PLUGIN_ROOT}/templates/decision-log.md shape):
    • Date (absolute, YYYY-MM-DD).
    • Bold one-line summary, then any detail. For product decisions, add "Owner decision".
    • Why: the constraint or evidence, not "preferred".
    • Source: the ticket, PR or question.
    • Accepted risks also get revisit when.
  3. If it reverses an earlier decision, mark the old row Superseded (YYYY-MM-DD) with a pointer to the new one. Never delete it.
  4. If it implies a rule, add one bullet to AGENTS.md in the right section.
  5. If it changes a ticket's scope, update the ticket description and say so in a comment.

Edit the Decision Log where AGENTS.md → "Tracker" says it lives (a tracker document, a Confluence page, or docs/decisions.md), following that section's editing notes. Insert right after the section's table header row.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.